Sublethal necroptosis signaling promotes inflammation and liver cancer.

It is currently not well known how necroptosis and necroptosis responses manifest in vivo. Here, we uncovered a molecular switch facilitating reprogramming between two alternative modes of necroptosis signaling in hepatocytes, fundamentally affecting immune responses and hepatocarcinogenesis. Concomitant necrosome and NF-κB activation in hepatocytes, which physiologically express low concentrations of receptor-interacting kinase 3 (RIPK3), did not lead to immediate cell death but forced them into a prolonged "sublethal" state with leaky membranes, functioning as secretory cells that released specific chemokines including CCL20 and MCP-1. This triggered hepatic cell proliferation as well as activation of procarcinogenic monocyte-derived macrophage cell clusters, contributing to hepatocarcinogenesis. In contrast, necrosome activation in hepatocytes with inactive NF-κB-signaling caused an accelerated execution of necroptosis, limiting alarmin release, and thereby preventing inflammation and hepatocarcinogenesis. Consistently, intratumoral NF-κB-necroptosis signatures were associated with poor prognosis in human hepatocarcinogenesis. Therefore, pharmacological reprogramming between these distinct forms of necroptosis may represent a promising strategy against hepatocellular carcinoma.

3-Dimensional Reconstruction From Histopathological Sections: A Systematic Review.

Although pathological tissue analysis is typically performed on single 2-dimensional (2D) histologic reference slides, 3-dimensional (3D) reconstruction from a sequence of histologic sections could provide novel opportunities for spatial analysis of the extracted tissue. In this review, we analyze recent works published after 2018 and report information on the extracted tissue types, the section thickness, and the number of sections used for reconstruction. By analyzing the technological requirements for 3D reconstruction, we observe that software tools exist, both free and commercial, which include the functionality to perform 3D reconstruction from a sequence of histologic images. Through the analysis of the most recent works, we provide an overview of the workflows and tools that are currently used for 3D reconstruction from histologic sections and address points for future work, such as a missing common file format or computer-aided analysis of the reconstructed model.

Artificial intelligence for contrast-enhanced ultrasound of the liver: a systematic review.

Introduction The research field of Artificial intelligence (AI) in medicine and especially in gastroenterology is rapidly progressing with the first AI tools entering routine clinical practice, for example in colorectal cancer screening. Contrast-enhanced ultrasound (CEUS) is a highly reliable, low-risk and low-cost diagnostic modality for the examination of the liver. However, doctors need many years of training and experience to master this technique and, despite all efforts to standardize CEUS, it is often believed to contain significant interrater variability. As has been shown for endoscopy, AI holds promise to support examiners at all training levels in their decision-making and efficiency. Methods In this systematic review, we analyzed and compared original research studies applying AI methods to CEUS examinations of the liver published between January 2010 and February 2024. We performed a structured literature search on PubMed, Web of Science and IEEE. Two independent reviewers screened the articles and subsequently extracted relevant methodological features, e.g. cohort size, validation process, machine learning algorithm used, as well as indicative performance measures from the included articles. Results We included 41 studies with most applying AI methods for classification tasks related to focal liver lesions. These included distinguishing benign vs. malignant or classifying the entity itself, while a few studies tried to classify tumor grading, microvascular invasion status or response to transcatheter arterial chemoembolization directly from CEUS. Some articles tried to segment or detect focal liver lesions, while others aimed to predict survival and recurrence after ablation. The majority (25/41) of studies used hand-picked and/or annotated images as data input to their models. We observed mostly good to high reported model performances with accuracies ranging between 58.6% and 98.9%, while noticing a general lack of external validation. Conclusion Even though multiple proof-of-concept studies for the application of AI methods to CEUS examinations of the liver exist and report high performance, more prospective, externally validated and multicenter research is needed to bring such algorithms from desk to bedside.

Clinical relevance of biomarkers in cholangiocarcinoma: critical revision and future directions.

Cholangiocarcinoma (CCA) is a malignant tumour arising from the biliary system. In Europe, this tumour frequently presents as a sporadic cancer in patients without defined risk factors and is usually diagnosed at advanced stages with a consequent poor prognosis. Therefore, the identification of biomarkers represents an utmost need for patients with CCA. Numerous studies proposed a wide spectrum of biomarkers at tissue and molecular levels. With the present paper, a multidisciplinary group of experts within the European Network for the Study of Cholangiocarcinoma discusses the clinical role of tissue biomarkers and provides a selection based on their current relevance and potential applications in the framework of CCA. Recent advances are proposed by dividing biomarkers based on their potential role in diagnosis, prognosis and therapy response. Limitations of current biomarkers are also identified, together with specific promising areas (ie, artificial intelligence, patient-derived organoids, targeted therapy) where research should be focused to develop future biomarkers.

Serum levels of soluble B and T lymphocyte attenuator predict overall survival in patients undergoing immune checkpoint inhibitor therapy for solid malignancies.

Therapy with immune checkpoint inhibitors (ICIs) can lead to durable tumor control in patients with various advanced stage malignancies. However, this is not the case for all patients, leading to an ongoing search for biomarkers predicting response and outcome to ICI. The B and T lymphocyte attenuator (BTLA) is an immune checkpoint expressed on immune cells that was shown to modulate therapeutic responses. Here, we evaluate circulating levels of its soluble form, soluble B and T lymphocyte attenuator (sBTLA), as a biomarker for the prediction of treatment response and outcome to ICI therapy. Serum levels of sBTLA were analyzed by multiplex immunoassay in n = 84 patients receiving ICI therapy for solid malignancies and 32 healthy controls. BTLA expression was evaluated on peripheral blood mononuclear cells in a subset of patients (n = 6) using multicolor flow cytometry. Baseline sBTLA serum levels were significantly higher in cancer patients compared to healthy controls. Importantly, circulating sBTLA levels were an independent prognostic factor for overall survival (OS). As such, patients with initial sBTLA levels above the calculated prognostic cutoff value (311.64 pg/mL) had a median OS of only 138 days compared to 526 for patients with sBTLA levels below this value (P = .001). Uni- and multivariate Cox regression analyses confirmed the prognostic role of sBTLA in the context of ICI therapy. Finally, we observed a significant correlation between sBTLA levels and the frequency of CD3 + CD8 + BTLA+ T cells in peripheral blood. Thus, our data suggest that circulating sBTLA could represent a noninvasive biomarker to predict outcome to ICI therapy, helping to select eligible therapy candidates.

High baseline soluble urokinase plasminogen activator receptor (suPAR) serum levels indicate adverse outcome after resection of pancreatic adenocarcinoma.

Surgical resection represents the only potentially curative therapy for patients with pancreatic adenocarcinoma (PDAC), an aggressive malignancy with a very limited 5-year survival rate. However, even after complete tumor resection, many patients are still facing an unfavorable prognosis underlining the need for better preoperative stratification algorithms. Here, we explored the role of the secreted glycoprotein soluble urokinase plasminogen activator receptor (suPAR) as a novel circulating biomarker for patients undergoing resection of PDAC. Serum levels of suPAR were measured by enzyme-linked immunosorbent assay (ELISA) in an exploratory as well as a validation cohort comprising a total of 127 PDAC patients and 75 healthy controls. Correlating with a cytoplasmic immunohistochemical expression of uPAR in PDAC tumor cells, serum levels of suPAR were significantly elevated in PDAC patients compared to healthy controls and patient with PDAC precursor lesions. Importantly, patients with high preoperative suPAR levels above a calculated cutoff value of 5.956 ng/ml showed a significantly reduced overall survival after tumor resection. The prognostic role of suPAR was further corroborated by uni- and multivariate Cox-regression analyses including parameters of systemic inflammation, liver and kidney function as well as clinico-pathological patients' characteristics. Moreover, high baseline suPAR levels identified those patients particularly susceptible to acute kidney injury and surgical complications after surgery. In conclusion, our data suggest that circulating suPAR represents a novel prognostic marker in PDAC patients undergoing tumor resection that might be a useful addition to existing preoperative stratification algorithms for identifying patients that particularly benefit from extended tumor resection.

Novel biomarker SARIFA in colorectal cancer: highly prognostic, not genetically driven and histologic indicator of a distinct tumor biology.

SARIFA (Stroma AReactive Invasion Front Areas) has recently emerged as a promising histopathological biomarker for colon and gastric cancer. To elucidate the underlying tumor biology, we assessed SARIFA-status in tissue specimens from The-Cancer-Genome-Atlas (TCGA) cohorts COAD (colonic adenocarcinoma) and READ (rectal adenocarcinoma). For the final analysis, 207 CRC patients could be included, consisting of 69 SARIFA-positive and 138 SARIFA-negative cases. In this external validation cohort, H&E-based SARIFA-positivity was strongly correlated with unfavorable overall, disease-specific, and progression-free survival, partly outperforming conventional prognostic factors. SARIFA-positivity was not associated with known high-risk genetic profiles, such as BRAF V600E mutations or microsatellite-stable status. Transcriptionally, SARIFA-positive CRCs exhibited an overlap with CRC consensus molecular subtypes CMS1 and CMS4, along with distinct differential gene expression patterns, linked to lipid metabolism and increased stromal cell infiltration scores (SIIS). Gene-expression-based drug sensitivity prediction revealed a differential treatment response in SARIFA-positive CRCs. In conclusion, SARIFA represents the H&E-based counterpart of an aggressive tumor biology, demonstrating a partial overlap with CMS1/4 and also adding a further biological layer related to lipid metabolism. Our findings underscore SARIFA-status as an ideal biomarker for refined patient stratification and novel drug developments, particularly given its cost-effective assessment based on routinely available H&E slides.

CpG-biomarkers in tumor tissue and prediction models for the survival of colorectal cancer: A systematic review and external validation study.

The research aimed to identify previously published CpG-methylation-based prognostic biomarkers and prediction models for colorectal cancer (CRC) prognosis and validate them in a large external cohort. A systematic search was conducted, analyzing 298 unique CpGs and 12 CpG-based prognostic models from 28 studies. After adjustment for clinical variables, 48 CpGs and five prognostic models were confirmed to be associated with survival. However, the discrimination ability of the models was insufficient, with area under the receiver operating characteristic curves ranging from 0.53 to 0.62. Calibration accuracy was mostly poor, and no significant added prognostic value beyond traditional clinical variables was observed. All prognostic models were rated at high risk of bias. While a fraction of CpGs showed potential clinical utility and generalizability, the CpG-based prognostic models performed poorly and lacked clinical relevance.

Developing a low-cost, open-source, locally manufactured workstation and computational pipeline for automated histopathology evaluation using deep learning.

BACKGROUND: Deployment and access to state-of-the-art precision medicine technologies remains a fundamental challenge in providing equitable global cancer care in low-resource settings. The expansion of digital pathology in recent years and its potential interface with diagnostic artificial intelligence algorithms provides an opportunity to democratize access to personalized medicine. Current digital pathology workstations, however, cost thousands to hundreds of thousands of dollars. As cancer incidence rises in many low- and middle-income countries, the validation and implementation of low-cost automated diagnostic tools will be crucial to helping healthcare providers manage the growing burden of cancer. METHODS: Here we describe a low-cost ($230) workstation for digital slide capture and computational analysis composed of open-source components. We analyze the predictive performance of deep learning models when they are used to evaluate pathology images captured using this open-source workstation versus images captured using common, significantly more expensive hardware. Validation studies assessed model performance on three distinct datasets and predictive models: head and neck squamous cell carcinoma (HPV positive versus HPV negative), lung cancer (adenocarcinoma versus squamous cell carcinoma), and breast cancer (invasive ductal carcinoma versus invasive lobular carcinoma). FINDINGS: When compared to traditional pathology image capture methods, low-cost digital slide capture and analysis with the open-source workstation, including the low-cost microscope device, was associated with model performance of comparable accuracy for breast, lung, and HNSCC classification. At the patient level of analysis, AUROC was 0.84 for HNSCC HPV status prediction, 1.0 for lung cancer subtype prediction, and 0.80 for breast cancer classification. INTERPRETATION: Our ability to maintain model performance despite decreased image quality and low-power computational hardware demonstrates that it is feasible to massively reduce costs associated with deploying deep learning models for digital pathology applications. Improving access to cutting-edge diagnostic tools may provide an avenue for reducing disparities in cancer care between high- and low-income regions. FUNDING: Funding for this project including personnel support was provided via grants from NIH/NCIR25-CA240134, NIH/NCIU01-CA243075, NIH/NIDCRR56-DE030958, NIH/NCIR01-CA276652, NIH/NCIK08-CA283261, NIH/NCI-SOAR25CA240134, SU2C (Stand Up to Cancer) Fanconi Anemia Research Fund - Farrah Fawcett Foundation Head and Neck Cancer Research Team Grant, and the European UnionHorizon Program (I3LUNG).

Converging deep learning and human-observed tumor-adipocyte interaction as a biomarker in colorectal cancer.

BACKGROUND: Tumor-Adipose-Feature (TAF) as well as SARIFA (Stroma AReactive Invasion Front Areas) are two histologic features/biomarkers linking tumor-associated adipocytes to poor outcomes in colorectal cancer (CRC) patients. Whereas TAF was identified by deep learning (DL) algorithms, SARIFA was established as a human-observed histopathologic biomarker. METHODS: To study the overlap between TAF and SARIFA, we performed a systematic pathological review of TAF based on all published image tiles. Additionally, we analyzed the presence/absence of TAF in SARIFA-negative CRC cases to elucidate the biologic and prognostic role of a direct tumor-adipocyte contact. TCGA-CRC gene expression data is investigated to assess the association of FABP4 (fatty-acid binding protein 4) and CD36 (fatty-acid translocase) with both TAF and CRC prognosis. RESULTS: By investigating the TAF/SARIFA overlap, we show that many TAF patches correspond to the recently described SARIFA-phenomenon. Even though there is a pronounced morphological and biological overlap, there are differences in the concepts. The presence of TAF in SARIFA-negative CRCs is not associated with poor outcomes in this cohort, potentially highlighting the importance of a direct tumor-adipocyte interaction. Upregulation of FABP4 and CD36 gene expression seem both linked to a poor prognosis in CRC. CONCLUSIONS: By proving the substantial overlap between human-observed SARIFA and DL-based TAF as morphologic biomarkers, we demonstrate that linking DL-based image features to independently developed histopathologic biomarkers is a promising tool in the identification of clinically and biologically meaningful biomarkers. Adipocyte-tumor-cell interactions seem to be crucial in CRC, which should be considered as biomarkers for further investigations.

Different methods exist in assessing samples removed from cancer patients during surgery. We linked two independently established tissue-based methods for determining the outcome of colorectal cancer patients together: tumor adipose feature (TAF) and Stroma AReactive Invasion Front Areas (SARIFA). SARIFA as biological feature was observed solely by humans and TAF was identified by the help of a computer algorithm. We examined TAF in many cancer slides and looked at whether they showed similarities to SARIFA. TAF often matched SARIFA, but not always. Interestingly, these methods could be used to predict outcomes for patients and are associated with specific gene expression involved in tumor and fat cell interaction. Our study shows that combining computer algorithms with human expertize in evaluating tissue samples can identify meaningful features in patient samples, which may help to predict the best treatment options.

Federated Learning for Decentralized Artificial Intelligence in Melanoma Diagnostics.

Importance: The development of artificial intelligence (AI)-based melanoma classifiers typically calls for large, centralized datasets, requiring hospitals to give away their patient data, which raises serious privacy concerns. To address this concern, decentralized federated learning has been proposed, where classifier development is distributed across hospitals. Objective: To investigate whether a more privacy-preserving federated learning approach can achieve comparable diagnostic performance to a classical centralized (ie, single-model) and ensemble learning approach for AI-based melanoma diagnostics. Design, Setting, and Participants: This multicentric, single-arm diagnostic study developed a federated model for melanoma-nevus classification using histopathological whole-slide images prospectively acquired at 6 German university hospitals between April 2021 and February 2023 and benchmarked it using both a holdout and an external test dataset. Data analysis was performed from February to April 2023. Exposures: All whole-slide images were retrospectively analyzed by an AI-based classifier without influencing routine clinical care. Main Outcomes and Measures: The area under the receiver operating characteristic curve (AUROC) served as the primary end point for evaluating the diagnostic performance. Secondary end points included balanced accuracy, sensitivity, and specificity. Results: The study included 1025 whole-slide images of clinically melanoma-suspicious skin lesions from 923 patients, consisting of 388 histopathologically confirmed invasive melanomas and 637 nevi. The median (range) age at diagnosis was 58 (18-95) years for the training set, 57 (18-93) years for the holdout test dataset, and 61 (18-95) years for the external test dataset; the median (range) Breslow thickness was 0.70 (0.10-34.00) mm, 0.70 (0.20-14.40) mm, and 0.80 (0.30-20.00) mm, respectively. The federated approach (0.8579; 95% CI, 0.7693-0.9299) performed significantly worse than the classical centralized approach (0.9024; 95% CI, 0.8379-0.9565) in terms of AUROC on a holdout test dataset (pairwise Wilcoxon signed-rank, P < .001) but performed significantly better (0.9126; 95% CI, 0.8810-0.9412) than the classical centralized approach (0.9045; 95% CI, 0.8701-0.9331) on an external test dataset (pairwise Wilcoxon signed-rank, P < .001). Notably, the federated approach performed significantly worse than the ensemble approach on both the holdout (0.8867; 95% CI, 0.8103-0.9481) and external test dataset (0.9227; 95% CI, 0.8941-0.9479). Conclusions and Relevance: The findings of this diagnostic study suggest that federated learning is a viable approach for the binary classification of invasive melanomas and nevi on a clinically representative distributed dataset. Federated learning can improve privacy protection in AI-based melanoma diagnostics while simultaneously promoting collaboration across institutions and countries. Moreover, it may have the potential to be extended to other image classification tasks in digital cancer histopathology and beyond.

A pilot study on the efficacy of GPT-4 in providing orthopedic treatment recommendations from MRI reports.

Large language models (LLMs) have shown potential in various applications, including clinical practice. However, their accuracy and utility in providing treatment recommendations for orthopedic conditions remain to be investigated. Thus, this pilot study aims to evaluate the validity of treatment recommendations generated by GPT-4 for common knee and shoulder orthopedic conditions using anonymized clinical MRI reports. A retrospective analysis was conducted using 20 anonymized clinical MRI reports, with varying severity and complexity. Treatment recommendations were elicited from GPT-4 and evaluated by two board-certified specialty-trained senior orthopedic surgeons. Their evaluation focused on semiquantitative gradings of accuracy and clinical utility and potential limitations of the LLM-generated recommendations. GPT-4 provided treatment recommendations for 20 patients (mean age, 50 years ± 19 [standard deviation]; 12 men) with acute and chronic knee and shoulder conditions. The LLM produced largely accurate and clinically useful recommendations. However, limited awareness of a patient's overall situation, a tendency to incorrectly appreciate treatment urgency, and largely schematic and unspecific treatment recommendations were observed and may reduce its clinical usefulness. In conclusion, LLM-based treatment recommendations are largely adequate and not prone to 'hallucinations', yet inadequate in particular situations. Critical guidance by healthcare professionals is obligatory, and independent use by patients is discouraged, given the dependency on precise data input.

Validation of the prognostic value of CD3 and CD8 cell densities analogous to the Immunoscore® by stage and location of colorectal cancer: an independent patient cohort study.

In addition to the traditional staging system in colorectal cancer (CRC), the Immunoscore® has been proposed to characterize the level of immune infiltration in tumor tissue and as a potential prognostic marker. The aim of this study was to examine and validate associations of an immune cell score analogous to the Immunoscore® with established molecular tumor markers and with CRC patient survival in a routine setting. Patients from a population-based cohort study with available CRC tumor tissue blocks were included in this analysis. CD3+ and CD8+ tumor infiltrating lymphocytes in the tumor center and invasive margin were determined in stained tumor tissue slides. Based on the T-cell density in each region, an  immune cell score closely analogous to the concept of the Immunoscore® was calculated and tumors categorized into IS-low, IS-intermediate, or IS-high. Logistic regression models were used to assess associations between clinicopathological characteristics with the immune cell score, and Cox proportional hazards models to analyze associations with cancer-specific, relapse-free, and overall survival. From 1,535 patients with CRC, 411 (27%) had IS-high tumors. Microsatellite instability (MSI-high) was strongly associated with higher immune cell score levels (p < 0.001). Stage I-III patients with IS-high had better CRC-specific and relapse-free survival compared to patients with IS-low (hazard ratio [HR] = 0.42 [0.27-0.66] and HR = 0.45 [0.31-0.67], respectively). Patients with microsatellite stable (MSS) tumors and IS-high had better survival (HRCSS  = 0.60 [0.42-0.88]) compared to MSS/IS-low patients. In this population-based cohort of CRC patients, the immune cell score was significantly associated with better patient survival. It was a similarly strong prognostic marker in patients with MSI-high tumors and in the larger group of patients with MSS tumors. Additionally, this study showed that it is possible to implement an analogous immune cell score approach and validate the Immunoscore® using open source software in an academic setting. Thus, the Immunoscore® could be useful to improve the traditional staging system in colon and rectal cancer used in clinical practice.

Deep learning trained on lymph node status predicts outcome from gastric cancer histopathology: a retrospective multicentric study.

AIM: Gastric cancer (GC) is a tumour entity with highly variant outcomes. Lymph node metastasis is a prognostically adverse biomarker. We hypothesised that GC primary tissue contains information that is predictive of lymph node status and patient prognosis and that this information can be extracted using deep learning (DL). METHODS: Using three patient cohorts comprising 1146 patients, we trained and validated a DL system to predict lymph node status directly from haematoxylin and eosin-stained GC tissue sections. We investigated the concordance between the DL-based prediction from the primary tumour slides (aiN score) and the histopathological lymph node status (pN). Furthermore, we assessed the prognostic value of the aiN score alone and when combined with the pN status. RESULTS: The aiN score predicted the pN status reaching area under the receiver operating characteristic curves of 0.71 in the training cohort and 0.69 and 0.65 in the two test cohorts. In a multivariate Cox analysis, the aiN score was an independent predictor of patient survival with hazard ratios of 1.5 in the training cohort and of 1.3 and 2.2 in the two test cohorts. A combination of the aiN score and the pN status prognostically stratified patients by survival with p-values <0.05 in logrank tests. CONCLUSION: GC primary tumour tissue contains additional prognostic information that is accessible using the aiN score. In combination with the pN status, this can be used for personalised management of GC patients after prospective validation.

Integration of deep learning-based image analysis and genomic data in cancer pathology: A systematic review.

BACKGROUND: Over the past decade, the development of molecular high-throughput methods (omics) increased rapidly and provided new insights for cancer research. In parallel, deep learning approaches revealed the enormous potential for medical image analysis, especially in digital pathology. Combining image and omics data with deep learning tools may enable the discovery of new cancer biomarkers and a more precise prediction of patient prognosis. This systematic review addresses different multimodal fusion methods of convolutional neural network-based image analyses with omics data, focussing on the impact of data combination on the classification performance. METHODS: PubMed was screened for peer-reviewed articles published in English between January 2015 and June 2021 by two independent researchers. Search terms related to deep learning, digital pathology, omics, and multimodal fusion were combined. RESULTS: We identified a total of 11 studies meeting the inclusion criteria, namely studies that used convolutional neural networks for haematoxylin and eosin image analysis of patients with cancer in combination with integrated omics data. Publications were categorised according to their endpoints: 7 studies focused on survival analysis and 4 studies on prediction of cancer subtypes, malignancy or microsatellite instability with spatial analysis. CONCLUSIONS: Image-based classifiers already show high performances in prognostic and predictive cancer diagnostics. The integration of omics data led to improved performance in all studies described here. However, these are very early studies that still require external validation to demonstrate their generalisability and robustness. Further and more comprehensive studies with larger sample sizes are needed to evaluate performance and determine clinical benefits.

Golgi Protein 73 (GP73) Serum Levels Predict Outcome after Resection of Biliary Tract Cancer.

BACKGROUND: Tumor resection represents the only potentially curative therapy for patients with biliary tract cancer. Nevertheless, disease recurrence is observed in about 50% of patients, leading to a 5-years survival rate of less than 50%. The Golgi protein 73 (GP73), a type II Golgi transmembrane protein, exerts important functions of intracellular protein processing and transportation. Circulating GP73 has recently been suggested as a prognostic marker following resection of hepatocellular carcinoma (HCC) but its role in the context of BTC has remained unknown. In this study, we evaluate a potential role of circulating GP73 as a novel biomarker in patients with resectable BTC. METHODS: GP73 serum levels were measured by immunoassay in n = 97 BTC and n = 40 HCC patients as well as n = 31 healthy controls. Results were correlated with clinical data. RESULTS: Serum GP73 levels were significantly elevated in BTC patients compared to healthy controls but lower compared to HCC patients. The combination of GP73/CA19-9 showed a sensitivity and specificity of 83.5% and 90.3% regarding the differentiation of BTC patients and healthy controls. BTC patients with baseline GP73 levels above the ideal cut-off value (42.47 ng/mL) showed a significantly reduced median overall survival (193 days) compared to patients with preoperative GP73 levels below this cut-off (882 days). These results were confirmed in uni- and multivariate Cox-regression analysis including several clinicopathological parameters such as age, ECOG performance status, tumor stage as well as established tumor markers and parameters of liver and kidney function. CONCLUSIONS: GP73 represents a previously unrecognized biomarker in the patients with resectable BTC that identifies patients with an impaired postoperative outcome. If larger clinical trials confirmed these findings, measurement of GP73 serum levels might become a novel tool in the challenging preoperative stratification process of patients with resectable BTC.

Artificial Intelligence-based Detection of FGFR3 Mutational Status Directly from Routine Histology in Bladder Cancer: A Possible Preselection for Molecular Testing?

BACKGROUND: Fibroblast growth factor receptor (FGFR) inhibitor treatment has become the first clinically approved targeted therapy in bladder cancer. However, it requires previous molecular testing of each patient, which is costly and not ubiquitously available. OBJECTIVE: To determine whether an artificial intelligence system is able to predict mutations of the FGFR3 gene directly from routine histology slides of bladder cancer. DESIGN, SETTING, AND PARTICIPANTS: We trained a deep learning network to detect FGFR3 mutations on digitized slides of muscle-invasive bladder cancers stained with hematoxylin and eosin from the Cancer Genome Atlas (TCGA) cohort (n = 327) and validated the algorithm on the "Aachen" cohort (n = 182; n = 121 pT2-4, n = 34 stroma-invasive pT1, and n = 27 noninvasive pTa tumors). OUTCOME MEASUREMENTS AND STATISTICAL ANALYSIS: The primary endpoint was the area under the receiver operating curve (AUROC) for mutation detection. Performance of the deep learning system was compared with visual scoring by an uropathologist. RESULTS AND LIMITATIONS: In the TCGA cohort, FGFR3 mutations were detected with an AUROC of 0.701 (p < 0.0001). In the Aachen cohort, FGFR3 mutants were found with an AUROC of 0.725 (p < 0.0001). When trained on TCGA, the network generalized to the Aachen cohort, and detected FGFR3 mutants with an AUROC of 0.625 (p = 0.0112). A subgroup analysis and histological evaluation found highest accuracy in papillary growth, luminal gene expression subtypes, females, and American Joint Committee on Cancer (AJCC) stage II tumors. In a head-to-head comparison, the deep learning system outperformed the uropathologist in detecting FGFR3 mutants. CONCLUSIONS: Our computer-based artificial intelligence system was able to detect genetic alterations of the FGFR3 gene of bladder cancer patients directly from histological slides. In the future, this system could be used to preselect patients for further molecular testing. However, analyses of larger, multicenter, muscle-invasive bladder cancer cohorts are now needed in order to validate and extend our findings. PATIENT SUMMARY: In this report, a computer-based artificial intelligence (AI) system was applied to histological slides to predict genetic alterations of the FGFR3 gene in bladder cancer. We found that the AI system was able to find the alteration with high accuracy. In the future, this system could be used to preselect patients for further molecular testing.